Research & Projects
(unfold drop-down for details)
(unfold drop-down for details)
Embed2Scale aims to research the potential of representation learning for federated geospatial applications across high-performance compute infrastructure. Self-supervised learning (cf. foundation models / Large-Language Models) transforms data such as a 1000x1000 = 1 million pixel image into a feature vector of, e.g., 1000 floating point values.
In a collaboration of the German Aerospace Center, IBM Research, Oxford University, Juelich Supercomputing Center, the European Union Satellite Center, Zurich University, Muenster University, and Sinergise/Planet, we explore the potential for compression by self-supervised learning on geospatial [DOI10.1109/MGRS.2022.3198244] data across data centers.
schematic workflow of distributed feature vector sharing across (geospatial) data centers
The broad spectrum of European satellite missions under the umbrella of the Copernicus Programme and the success of deep learning in computer vision call for a test of multi-sensor data fusion with artificial neural networks. As part of the EvoLand consortium with Vito, GAF AG, CESBIO/CNES, CLS, the German Aerospace Center, Joanneum Research, and Sinergise/Planet, we explore the potential and limitations of land use mapping with deep learning for real-world industry use cases.
semantic segmentation (right, forest in green) of rural scene (left)
AutoGeoLabel since 2021, research theme
Open-Source, Auto-Generated Labels for Machine Learning in Urban Spaces
How may we exploit high-quality remote sensing data (such as LiDAR) and incomplete crowdsourcing annotations (such as OpenStreetMap), to automatically label geospatial, multi-spectral imagery? To answer that question, we study noise-robust training of deep neural networks for semantic segmentation of geospatial (urban) scenes, e.g.:
automatic classification of local climate zones from LiDAR data [DOI:10.48550/arXiv.2405.13993]
adaptively correct incomplete building footprint labels while training a deep neural network for semantic segmentation [DOI:10.1109/TGRS.2024.3373908]
auto-generated urban labels from airborne LiDAR [DOI:10.1109/BigData52589.2021.9672060]
monitoring the impact of Hurricane Sandy from auto-generated vegetation labels [DOI:10.1109/IGARSS46834.2022.9884017]
early stopping strategy for training a semantic segmentation model on noisy labels generated by an airborne LiDAR survey [DOI:10.1109/BigData55660.2022.10020164]
a novel methodology for unsupervised generative modelling of remote sensor correlation with proof-of-concept for urban heat island analysis [DOI:10.1109/IGARSS52108.2023.10281573]
OpenStreetMap label-generation from style transfer of high-resolution overhead imagery to rasterized maps [DOI:10.1145/3394486.3403301], DOI:10.3390/ijgi9070427]
LiDAR point cloud (top left) in Williamsburg, New York City with corresponding map below (green vegetation, yellow roads, red buildings)
SSL4EO since 2021, research theme
Multi-Modal Data Fusion with Self-Supervised Deep Learning
While remote sensing streams petabytes of optical, radar, and LiDAR (laser) data for various Earth observation (EO) applications, human labeling and efficient multi-modal data fusion to train deep neural networks poses a major challenge. With my students, we research self-supervised learning (SSL) methodologies for representation learning (feature vectors) of remote sensing information, e.g.:
autoencoder-generated feature vectors from reconstructing classical computer vision features [DOI:10.48550/arXiv.2310.18653]
interpretation of SSL feature vectors for radar-optical fusion [DOI:10.48550/arXiv.2309.05300]
radar-optical neural networks fusion robust to missing a modality [DOI:10.1109/IGARSS46834.2022.9883983]
label-assisted SSL for hyperspectral image segmentation [DOI:10.1109/IGARSS52108.2023.10282971]
benchmark dataset and models (convolutional neural networks and vision transformers) for radar-optical data fusion [DOI:10.1109/MGRS.2023.32816511]
illustration of diversity in the SSL4EO-S12 benchmark dataset spatio-temporally aligning Sentinel-1 and Sentinel-2 imagery
AI4Archaeology since 2019, research theme
Uncovering Ancient Treasures with Large-Scale Data Mining
Remote sensing such as aerial imaging and airborne LiDAR surveys provide a versatile tool to scan large areas for ancient artifacts. However, a major technical challenge poses the low signal-to-noise ratio (artifact erosion) and the little amount of available labels (scarcity of artifacts). In close collaboration with IBM Research, I develop machine learning pipelines to guide archaeologists in their field work, e.g.:
Nasca UNESCO World Heritage, Peru: protection of geoglyphs from flood events [DOI:10.48550/arXiv.2405.11814]
Angamacu city, Mexico: identification of eroded buildings buried under vegetation [DOI:10.1109/BigData47090.2019.9005548]
Negev desert agriculture, Israel: identification of ancient agricultural terraces [DOI:10.1109/BigData55660.2022.10020329]
pottery fragments of the Nasca culture, Peru
AI4GreenSpaces since 2021, research theme
Biomass Mapping at all Scales
Carbon sequestration through trees is a natural approach with additional benefit for local climate zones and biodiversity. On various scales, I collaborate in projects to estimate biomass from remote sensing data, e.g.:
study the cooling potential of trees in various urban scenarios thermal band of Landsat 8 satellite and Local Climate Zones [FragileEarth@KDD2022]
carbon sequestration of urban forests [ClimateChangeAI@ICML2021]
estimate biomass from single tree height through Gaussian process [DOI:/10.1109/JSTARS.2023.3271186]
continent-scale biomass estimation with physics-informed deep neural network [ClimateChangeAI@NEURIPS2022], [DOI:10.1109/IGARSS52108.2023.10282838]
3D point cloud of LiDAR data covering a patch of 20m x 40m of forest (green) in uneven terrain (brown)
IBM PAIRS 2015-2021, corporate research
Petabyte-Scale Geospatial Analytics: Platform & Applications
Complex geospatial analytics requires scalable infrastructure and distributed software to index, process, and fuse data spatio-temporal information. I contributed the following innovations:
efficient cross-layer spatio-temporal queries through overviews [Patent:US11360970B2]
vector-raster data fusion method [Patent:US11594004B2]
spatio-temporal vector-raster data query system [Patent:US11204896B2]
Employing open-source technologies such as Apache HBase, Hadoop, and Spark, I co-developed, tested, and employed a platform for Earth observation data science, cf.:
platform implementation, benchmark, and use case demonstration [DOI:10.1109/BigData.2015.7363884], [DOI:10.5194/isprs-archives-XLII-3-W12-2020-255-2020], [DOI:10.1109/BigData.2016.7840910]
novel temporal clustering algorithm [DOI:10.1109/BigData.2017.825849f], [Patent:US10706080B2]
application for agriculture [DOI:10.1147/JRD.2016.2591698], infrastructure risk assessment [DOI:10.1109/BigData47090.2019.9006600], and disaster management DOI:10.1147/JRD.2020.2970903
Phys.org blog post on IBM PAIRS
open-source IBM PAIRS API on GitHub: https://github.com/IBM/ibmpairs
my 2021 presentation of IBM PAIRS on YouTube
YouTube recordings of my 2022 presentation on open-source stacks for geospatial data platforms at the 2nd NASA workshop on Open Source Science for the Earth System Observatory Mission
raster (top) to vector (bottom) data fusion by grid indexing (middle) for large-scale geo-data-format queries